© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8510
    Prev
    Next
    INDEX
    Explanations

    reporting services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perguntas
    -1.25
     suscit
    -1.23
    Recuerda
    -1.19
     multicolore
    -1.16
    😂😂😂😂
    -1.16
    مزید
    -1.16
    STERY
    -1.15
     grotte
    -1.15
    кими
    -1.14
     enthou
    -1.14
    POSITIVE LOGITS
    XtraReports
    1.46
    </i>
    1.35
     発
    1.23
    忡
    1.22
    ufel
    1.22
    ِّ
    1.22
     acoged
    1.20
     wyś
    1.19
     lavoro
    1.18
     embalaje
    1.17
    Activations Density 0.016%

    No Known Activations